orchestration
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime path uses
orca orchestration check/inboxto ingest inter-agent messages from Orca’s SQLite mail store, and those messages’--body/--payloadcontent is authored by other agents (outsider terminals), which can include free text that the coordinator then feeds into its LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata